In [1]:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import ticker  as ticker
import folium
import branca
from datetime import datetime, timedelta,date
import plotly.express as px
import calmap
import matplotlib.ticker as ticker
from mpl_toolkits.mplot3d import Axes3D
In [2]:
a=pd.read_csv(r'E:\Dataset\Medical.csv', skiprows=2)
pd.set_option('display.max_colwidth', None)
pd.set_option("display.max_columns",None)
pd.set_option("display.max_rows",None)
In [3]:
a=a.drop(['Footnotes'],axis=1)
a.drop(a.loc[53:58].index,inplace=True)
In [4]:
a['Medicare Beneficiaries as a Share of Total Population'] = pd.Series(["{0:.0f}%".format(val * 100/1) for val in a['Medicare Beneficiaries as a Share of Total Population']])
In [5]:
a.head(5)
Out[5]:
Location Medicare Beneficiaries as a Share of Total Population
0 United States 18%
1 Alabama 21%
2 Alaska 13%
3 Arizona 18%
4 Arkansas 21%
In [6]:
a['Medicare Beneficiaries as a Share of Total Population'] = a['Medicare Beneficiaries as a Share of Total Population'].str.rstrip('%')
In [ ]:
 
In [7]:
a['Medicare Beneficiaries as a Share of Total Population']=a['Medicare Beneficiaries as a Share of Total Population'].astype(int)
In [8]:
a.dtypes
Out[8]:
Location                                                 object
Medicare Beneficiaries as a Share of Total Population     int32
dtype: object
In [9]:
a.head(5)
Out[9]:
Location Medicare Beneficiaries as a Share of Total Population
0 United States 18
1 Alabama 21
2 Alaska 13
3 Arizona 18
4 Arkansas 21
In [10]:
a.shape
Out[10]:
(53, 2)
In [11]:
plt.style.use("ggplot")
a= a.sort_values('Medicare Beneficiaries as a Share of Total Population')
ax = a.plot(kind='barh',figsize=(10,10),edgecolor=None)
#f= plt.figure(figsize=(10,10))
#ax=f.add_subplot(1,1,1)


#a.sort_values(by='Medicare Beneficiaries as a Share of Total Population',ascending=True)
ax.set_yticklabels(a['Location'])
#ax.get_yticklabels()[1].set_color("red")
#ax.tick_params(size=5)

#ax=plt.barh(a['Location'],a['Medicare Beneficiaries as a Share of Total Population'])
#ax=plt.tick_params(size=5,labelsize = 10)
for p in ax.patches:
    width = p.get_width()
    height = p.get_height()
    x, y = p.get_xy()  
    ax.annotate(f'{width:.0f}%', (x + width*1.02, y + height/2), ha='center')
    
plt.xlabel("Percent",fontsize=18)
plt.title("Medicare Beneficiaries as a Share of Total Population in %",fontsize=20)
plt.tight_layout()

ax.xaxis.set_major_formatter(ticker.PercentFormatter(decimals=0))
#ax.xaxis.set_major_formatter(ticker.PercentFormatter())
#ax.xaxis.set_major_locator(ticker.MultipleLocator())
#ax.xaxis.set_minor_locator(ticker.MultipleLocator())
plt.xlabel("Percent",fontsize=18)
plt.title("Medicare Beneficiaries as a Share of Total Population in %",fontsize=20)
plt.tight_layout()
ax.get_legend().remove()
In [12]:
b=pd.read_csv(r'E:\Dataset\raw_data (3).csv', skiprows=2)
pd.set_option('display.max_colwidth', None)
pd.set_option("display.max_columns",None)
pd.set_option("display.max_rows",None)
In [13]:
b=b.drop(['Footnotes'],axis=1)
b.drop(b.loc[57:68].index,inplace=True)
In [14]:
#b.style.background_gradient(cmap='Blues',subset=["Original Medicare"])\
                   #.background_gradient(cmap='Reds',subset=["Medicare Advantage"])\
                    #.background_gradient(cmap='Greens',subset=["Total"])
b.style.format({'Original Medicare': '{:,.0f}','Medicare Advantage': '{:,.0f}','Total': '{:,.0f}'})\
                .background_gradient(cmap='Blues',subset=["Original Medicare"])\
                .background_gradient(cmap='Reds',subset=["Medicare Advantage"])\
                .background_gradient(cmap='Greens',subset=["Total"])
Out[14]:
Location Original Medicare Medicare Advantage Total
0 United States 40,008,858 19,860,544 59,869,402
1 Alabama 654,501 391,201 1,045,702
2 Alaska 94,737 746 95,483
3 Arizona 792,963 486,758 1,279,721
4 Arkansas 502,380 143,714 646,094
5 California 3,762,104 2,462,728 6,224,832
6 Colorado 586,694 324,951 911,645
7 Connecticut 446,216 233,139 679,355
8 Delaware 175,265 26,391 201,656
9 District of Columbia 79,809 15,525 95,334
10 Florida 2,593,338 1,922,172 4,515,510
11 Georgia 1,113,944 607,604 1,721,548
12 Hawaii 148,733 120,245 268,978
13 Idaho 225,109 98,769 323,878
14 Illinois 1,750,313 489,342 2,239,655
15 Indiana 903,265 352,022 1,255,287
16 Iowa 508,364 115,063 623,427
17 Kansas 450,288 82,931 533,219
18 Kentucky 664,989 266,487 931,476
19 Louisiana 572,878 294,948 867,826
20 Maine 235,925 100,397 336,322
21 Maryland 915,375 118,007 1,033,382
22 Massachusetts 1,042,302 283,905 1,326,207
23 Michigan 1,301,774 762,932 2,064,706
24 Minnesota 447,910 569,888 1,017,798
25 Mississippi 501,276 105,370 606,646
26 Missouri 840,260 398,455 1,238,715
27 Montana 188,337 39,140 227,477
28 Nebraska 298,774 45,426 344,200
29 Nevada 339,081 179,979 519,060
30 New Hampshire 260,617 35,081 295,698
31 New Jersey 1,262,994 359,537 1,622,531
32 New Mexico 279,122 138,316 417,438
33 New York 2,207,942 1,404,243 3,612,185
34 North Carolina 1,322,690 643,616 1,966,306
35 North Dakota 107,887 22,132 130,019
36 Ohio 1,469,964 860,971 2,330,935
37 Oklahoma 608,007 134,929 742,936
38 Oregon 484,589 371,483 856,072
39 Pennsylvania 1,625,172 1,099,881 2,725,053
40 Rhode Island 139,089 80,788 219,877
41 South Carolina 786,270 265,685 1,051,955
42 South Dakota 140,854 33,163 174,017
43 Tennessee 855,439 496,096 1,351,535
44 Texas 2,632,035 1,458,533 4,090,568
45 Utah 254,031 135,734 389,765
46 Vermont 132,287 13,566 145,853
47 Virginia 1,238,748 273,981 1,512,729
48 Washington 932,997 413,188 1,346,185
49 West Virginia 326,613 117,257 443,870
50 Wisconsin 699,652 461,428 1,161,080
51 Wyoming 104,955 2,701 107,656
52 American Samoa 6,725 11 6,736
53 Guam 16,995 0 16,995
54 Northern Mariana Islands nan nan nan
55 Puerto Rico 230,297 562,758 793,055
56 Virgin Islands 20,825 32 20,857
In [15]:
c=pd.read_csv(r'E:\Dataset\raw_data (4).csv', skiprows=2)
pd.set_option('display.max_colwidth', None)
pd.set_option("display.max_columns",None)
pd.set_option("display.max_rows",None)
In [16]:
c=c.drop(['Footnotes'], axis = 1)
c.drop(c.loc[52:61].index,inplace=True)
In [17]:
c.head()
Out[17]:
Location Race Categories Include Hispanic Individuals White % of Cases White % of Total Population Black % of Cases Black % of Total Population Hispanic % of Cases Hispanic % of Total Population Asian % of Cases Asian % of Total Population American Indian or Alaska Native % of Cases American Indian or Alaska Native % of Total Population Native Hawaiian or Other Pacific Islander % of Cases Native Hawaiian or Other Pacific Islander % of Total Population Other % of Cases Other % of Total Population Unknown Race % of Cases Unknown Ethnicity% of Cases
0 Alabama Yes 0.32 0.68 0.26 0.27 0.06 0.04 <.01 0.01 NR <.01 NR NaN 0.06 0.04 0.35 0.46
1 Alaska Yes 0.23 0.64 0.03 0.03 0.06 0.07 0.02 0.06 0.13 0.16 0.04 0.01 0.06 0.10 0.48 0.59
2 Arizona NaN 0.23 0.54 0.03 0.04 0.3 0.32 0.01 0.03 0.06 0.04 NR <.01 0.03 0.02 0.34 0.34
3 Arkansas Yes 0.55 0.77 0.22 0.15 0.22 0.08 0.01 0.02 <.01 0.01 0.04 <.01 0.09 0.06 0.08 0
4 California NaN 0.11 0.37 0.03 0.05 0.4 0.39 0.04 0.15 <.01 <.01 <.01 <.01 0.08 0.03 0.33 0.33
In [18]:
c.dtypes
Out[18]:
Location                                                            object
Race Categories Include Hispanic Individuals                        object
White % of Cases                                                    object
White % of Total Population                                        float64
Black % of Cases                                                    object
Black % of Total Population                                         object
Hispanic % of Cases                                                 object
Hispanic % of Total Population                                     float64
Asian % of Cases                                                    object
Asian % of Total Population                                        float64
American Indian or Alaska Native % of Cases                         object
American Indian or Alaska Native % of Total Population              object
Native Hawaiian or Other Pacific Islander % of Cases                object
Native Hawaiian or Other Pacific Islander % of Total Population     object
Other % of Cases                                                    object
Other % of Total Population                                        float64
Unknown Race % of Cases                                             object
Unknown Ethnicity% of Cases                                         object
dtype: object
In [19]:
c=c.replace(['NR', '<.01'],  [0, .01]) 
c=c.replace(np.nan,0)
c['White % of Cases'] = c['White % of Cases'].astype(float)
In [20]:
c.sample()
Out[20]:
Location Race Categories Include Hispanic Individuals White % of Cases White % of Total Population Black % of Cases Black % of Total Population Hispanic % of Cases Hispanic % of Total Population Asian % of Cases Asian % of Total Population American Indian or Alaska Native % of Cases American Indian or Alaska Native % of Total Population Native Hawaiian or Other Pacific Islander % of Cases Native Hawaiian or Other Pacific Islander % of Total Population Other % of Cases Other % of Total Population Unknown Race % of Cases Unknown Ethnicity% of Cases
8 District of Columbia Yes 0.21 0.42 0.51 0.46 0.26 0.11 0.02 0.04 0.01 0.01 0.01 0 0.23 0.08 0.02 0.09
In [21]:
c=c.drop(['Race Categories Include Hispanic Individuals'],axis=1)
In [22]:
#c.iloc[:, 1:18].apply(pd.to_numeric).head()
c.loc[:, c.columns != 'Location']=c.loc[:, c.columns != 'Location'].apply(pd.to_numeric)
In [23]:
c.dtypes
Out[23]:
Location                                                            object
White % of Cases                                                   float64
White % of Total Population                                        float64
Black % of Cases                                                   float64
Black % of Total Population                                        float64
Hispanic % of Cases                                                float64
Hispanic % of Total Population                                     float64
Asian % of Cases                                                   float64
Asian % of Total Population                                        float64
American Indian or Alaska Native % of Cases                        float64
American Indian or Alaska Native % of Total Population             float64
Native Hawaiian or Other Pacific Islander % of Cases               float64
Native Hawaiian or Other Pacific Islander % of Total Population    float64
Other % of Cases                                                   float64
Other % of Total Population                                        float64
Unknown Race % of Cases                                            float64
Unknown Ethnicity% of Cases                                        float64
dtype: object
In [24]:
c[c.select_dtypes(include=['number']).columns] *= 100
In [25]:
c.head()
Out[25]:
Location White % of Cases White % of Total Population Black % of Cases Black % of Total Population Hispanic % of Cases Hispanic % of Total Population Asian % of Cases Asian % of Total Population American Indian or Alaska Native % of Cases American Indian or Alaska Native % of Total Population Native Hawaiian or Other Pacific Islander % of Cases Native Hawaiian or Other Pacific Islander % of Total Population Other % of Cases Other % of Total Population Unknown Race % of Cases Unknown Ethnicity% of Cases
0 Alabama 32.0 68.0 26.0 27.0 6.0 4.0 1.0 1.0 0.0 1.0 0.0 0.0 6.0 4.0 35.0 46.0
1 Alaska 23.0 64.0 3.0 3.0 6.0 7.0 2.0 6.0 13.0 16.0 4.0 1.0 6.0 10.0 48.0 59.0
2 Arizona 23.0 54.0 3.0 4.0 30.0 32.0 1.0 3.0 6.0 4.0 0.0 1.0 3.0 2.0 34.0 34.0
3 Arkansas 55.0 77.0 22.0 15.0 22.0 8.0 1.0 2.0 1.0 1.0 4.0 1.0 9.0 6.0 8.0 0.0
4 California 11.0 37.0 3.0 5.0 40.0 39.0 4.0 15.0 1.0 1.0 1.0 1.0 8.0 3.0 33.0 33.0
In [26]:
jj=c.iloc[:,0]
sk=c.iloc[:,1]
pk=c.iloc[:,2]
kl=c.iloc[:,3]
jk=c.iloc[:,4]
fk=c.iloc[:,5]
wek=c.iloc[:,6]
gh=c.iloc[:,7]
ds=c.iloc[:,8]
gf=c.iloc[:,9]
gr=c.iloc[:,10]
cv=c.iloc[:,11]
hf=c.iloc[:,12]
sc=c.iloc[:,13]
wd=c.iloc[:,14]
ty=c.iloc[:,15]
uj=c.iloc[:,16]
index=np.arange(len(c))

plt.figure(figsize=(17,10))

#graph=plt.barh(y=index,width=sk)
#graph1=plt.barh(y=index,width=pk,left=sk)

graph=plt.bar(x=index,height=sk)
graph1=plt.bar(x=index,height=pk,bottom=sk)
graph2=plt.bar(x=index,height=kl,bottom=pk+sk)
graph3=plt.bar(x=index,height=jk,bottom=sk+pk+kl)
grap4=plt.bar(x=index,height=fk,bottom=sk+pk+kl+jk)
graph5=plt.bar(x=index,height=wek,bottom=sk+pk+kl+jk+fk)
grap6=plt.bar(x=index,height=gh,bottom=sk+pk+kl+jk+fk+wek)
graph7=plt.bar(x=index,height=ds,bottom=sk+pk+kl+jk+fk+wek+gh)
grap8=plt.bar(x=index,height=gf,bottom=sk+pk+kl+jk+fk+wek+gh+ds)
graph9=plt.bar(x=index,height=gr,bottom=sk+pk+kl+jk+fk+wek+gh+ds+gf)
graph10=plt.bar(x=index,height=cv,bottom=sk+pk+kl+jk+fk+wek+gh+ds+gf+gr)
graph11=plt.bar(x=index,height=hf,bottom=sk+pk+kl+jk+fk+wek+gh+ds+gf+gr+cv)
graph12=plt.bar(x=index,height=sc,bottom=sk+pk+kl+jk+fk+wek+gh+ds+gf+gr+cv+hf)
graph13=plt.bar(x=index,height=wd,bottom=sk+pk+kl+jk+fk+wek+gh+ds+gf+gr+cv+hf+sc)
graph14=plt.bar(x=index,height=ty,bottom=sk+pk+kl+jk+fk+wek+gh+ds+gf+gr+cv+hf+sc+wd)
graph15=plt.bar(x=index,height=uj,bottom=sk+pk+kl+jk+fk+wek+gh+ds+gf+gr+cv+hf+sc+wd+ty)

plt.xticks(index,jj,rotation=90)
plt.tight_layout()
plt.show()
In [27]:
d=pd.read_csv(r'E:\Dataset\raw_data (6).csv', skiprows=2)
pd.set_option('display.max_colwidth', None)
pd.set_option("display.max_columns",None)
pd.set_option("display.max_rows",None)
In [28]:
d=d.drop(['Footnotes'], axis = 1)
d.drop(d.loc[57:].index,inplace=True)
In [29]:
d.head()
Out[29]:
Location Number of COVID-19 Cases COVID-19 Cases per 1,000,000 Population Deaths from COVID-19 COVID-19 Deaths per 1,000,000 Population COVID-19 Fatality Rate
0 United States 6,187,336 18850.0 187,464 571.0 0.030298
1 Alabama 130,393 26594.0 2,266 462.0 0.017378
2 Alaska 5,584 7633.0 40 55.0 0.007163
3 Arizona 204,681 28120.0 5,171 710.0 0.025264
4 Arkansas 63,081 20903.0 861 285.0 0.013649
In [30]:
d.dtypes
Out[30]:
Location                                     object
Number of COVID-19 Cases                     object
COVID-19 Cases per 1,000,000 Population     float64
Deaths from COVID-19                         object
COVID-19 Deaths per 1,000,000 Population    float64
COVID-19 Fatality Rate                      float64
dtype: object
In [31]:
#d.loc[:, d.columns != 'Location']=d.loc[:, d.columns != 'Location'].apply(pd.to_numeric)
#d['Number of COVID-19 Cases']= (d['Number of COVID-19 Cases'].str.split()).apply(lambda x: float(d[:,1].replace(',','')))

d=d.replace(",","",regex=True)
In [32]:
d.sample()
Out[32]:
Location Number of COVID-19 Cases COVID-19 Cases per 1,000,000 Population Deaths from COVID-19 COVID-19 Deaths per 1,000,000 Population COVID-19 Fatality Rate
46 Utah 53839 16793.0 419 131.0 0.007782
In [33]:
d.loc[:, d.columns != 'Location']=d.loc[:, d.columns != 'Location'].apply(pd.to_numeric)
In [34]:
d.dtypes
Out[34]:
Location                                     object
Number of COVID-19 Cases                      int64
COVID-19 Cases per 1,000,000 Population     float64
Deaths from COVID-19                          int64
COVID-19 Deaths per 1,000,000 Population    float64
COVID-19 Fatality Rate                      float64
dtype: object
In [35]:
d.style.background_gradient(cmap='Blues',subset=["Number of COVID-19 Cases"])\
                        .background_gradient(cmap='Reds',subset=["COVID-19 Cases per 1,000,000 Population"])\
                        .background_gradient(cmap='Greens',subset=["Deaths from COVID-19"])\
                        .background_gradient(cmap='Purples',subset=["COVID-19 Deaths per 1,000,000 Population"])\
                        .background_gradient(cmap='Pastel1_r',subset=["COVID-19 Fatality Rate"])\
                        .format("{:.0f}",subset=["COVID-19 Deaths per 1,000,000 Population","Deaths from COVID-19","COVID-19 Cases per 1,000,000 Population","Number of COVID-19 Cases"])
Out[35]:
Location Number of COVID-19 Cases COVID-19 Cases per 1,000,000 Population Deaths from COVID-19 COVID-19 Deaths per 1,000,000 Population COVID-19 Fatality Rate
0 United States 6187336 18850 187464 571 0.030298
1 Alabama 130393 26594 2266 462 0.017378
2 Alaska 5584 7633 40 55 0.007163
3 Arizona 204681 28120 5171 710 0.025264
4 Arkansas 63081 20903 861 285 0.013649
5 California 728415 18435 13560 343 0.018616
6 Colorado 58267 10118 1955 339 0.033552
7 Connecticut 53365 14968 4468 1253 0.083725
8 Delaware 17752 18230 606 622 0.034137
9 District of Columbia 14186 20101 611 866 0.043071
10 Florida 640211 29808 11750 547 0.018353
11 Georgia 279354 26311 5931 559 0.021231
12 Hawaii 9202 6499 79 56 0.008585
13 Idaho 32927 18425 372 208 0.011298
14 Illinois 247260 19513 8360 660 0.033811
15 Indiana 97884 14540 3350 498 0.034224
16 Iowa 68203 21617 1141 362 0.016729
17 Kansas 44878 15404 473 162 0.010540
18 Kentucky 50885 11390 976 218 0.019181
19 Louisiana 151473 32583 5035 1083 0.033240
20 Maine 4633 3447 134 100 0.028923
21 Maryland 110831 18332 3789 627 0.034187
22 Massachusetts 121758 17665 9100 1320 0.074738
23 Michigan 116280 11643 6797 681 0.058454
24 Minnesota 78966 14002 1899 337 0.024048
25 Mississippi 85939 28876 2558 859 0.029765
26 Missouri 91175 14856 1604 261 0.017593
27 Montana 8019 7503 114 107 0.014216
28 Nebraska 35469 18336 404 209 0.011390
29 Nevada 70712 22957 1375 446 0.019445
30 New Hampshire 7368 5419 432 318 0.058632
31 New Jersey 193422 21776 15978 1799 0.082607
32 New Mexico 25812 12310 791 377 0.030645
33 New York 437971 22514 32982 1695 0.075306
34 North Carolina 174253 16614 2839 271 0.016292
35 North Dakota 12973 17024 150 197 0.011562
36 Ohio 128444 10988 4248 363 0.033073
37 Oklahoma 62040 15679 846 214 0.013636
38 Oregon 27336 6481 470 111 0.017193
39 Pennsylvania 142495 11131 7735 604 0.054283
40 Rhode Island 22243 20997 1055 996 0.047431
41 South Carolina 123325 23953 2846 553 0.023077
42 South Dakota 14596 16499 170 192 0.011647
43 Tennessee 160597 23516 1837 269 0.011439
44 Texas 646545 22298 13300 459 0.020571
45 USVI 1150 nan 16 nan 0.013913
46 Utah 53839 16793 419 131 0.007782
47 Vermont 1642 2631 58 93 0.035323
48 Virginia 124738 14614 2662 312 0.021341
49 Washington 75856 9962 1945 255 0.025641
50 West Virginia 11042 6161 245 137 0.022188
51 Wisconsin 77856 13372 1146 197 0.014719
52 Wyoming 3941 6809 41 71 0.010403
53 American Samoa 0 nan 0 nan 0.000000
54 Guam 1619 nan 14 nan 0.008647
55 Northern Mariana Islands 57 nan 2 nan 0.035088
56 Puerto Rico 34241 10721 455 142 0.013288
In [36]:
e=pd.read_csv(r'E:\Dataset\raw_data (14).csv', skiprows=2)
pd.set_option('display.max_colwidth', None)
pd.set_option("display.max_columns",None)
pd.set_option("display.max_rows",None)
In [37]:
e.drop(e.loc[52:].index,inplace=True)
#e.drop(e.index[0], inplace=True)
e.drop(e.head(1).index,inplace=True)
e.reset_index(drop=True,inplace=True)
In [38]:
e.sample(5)
Out[38]:
Location Total Hospitals
13 Illinois 187.0
43 Texas 523.0
3 Arkansas 88.0
16 Kansas 139.0
15 Iowa 118.0
In [39]:
abbreviation=pd.read_csv(r'E:\Downloads\csvData.csv')
In [40]:
abbreviation.head()
Out[40]:
State Abbrev Code
0 Alabama Ala. AL
1 Alaska Alaska AK
2 Arizona Ariz. AZ
3 Arkansas Ark. AR
4 California Calif. CA
In [41]:
newdf= pd.concat([e,abbreviation['Code']], axis = 1, levels=0).sort_index(axis=1)
In [42]:
newdf.head()
Out[42]:
Code Location Total Hospitals
0 AL Alabama 101.0
1 AK Alaska 21.0
2 AZ Arizona 83.0
3 AR Arkansas 88.0
4 CA California 359.0
In [43]:
fig = px.choropleth(newdf,  # Input Pandas DataFrame
                    locations="Code",  # DataFrame column with locations
                    color_continuous_scale="Viridis",
                    color='Total Hospitals',
                    #range_color=(0, 12),  # DataFrame column with color values
                    hover_name="Location", # DataFrame column hover info
                    locationmode = 'USA-states') # Set to plot as US States
fig.update_layout(
    title_text = 'Total Number of Hospitals in each State', # Create a Title
    geo_scope='usa',  # Plot only the USA instead of globe
)
In [44]:
f=pd.read_csv(r'E:\Dataset\raw_data (15).csv', skiprows=2)
pd.set_option('display.max_colwidth', None)
pd.set_option("display.max_columns",None)
pd.set_option("display.max_rows",None)
In [45]:
f.drop(f.loc[52:].index,inplace=True)
f.drop(f.head(1).index,inplace=True)
f.reset_index(drop=True,inplace=True)
In [46]:
f.head()
Out[46]:
Location Total Hospital Beds Beds per 1,000 Population
0 Alabama 15278.0 3.1
1 Alaska 1636.0 2.2
2 Arizona 13846.0 1.9
3 Arkansas 9517.0 3.2
4 California 72511.0 1.8
In [47]:
fig, ax = plt.subplots()

#vals = np.array([[60., 32.], [37., 40.], [29., 10.]])
labels = f['Location']
sizes = f['Total Hospital Beds']
labels_vegefruit = f['Location']
sizes_vegefruit = f['Beds per 1,000 Population']

size=0.3


cmap = plt.get_cmap("tab20c")
outer_colors = cmap(np.arange(3)*4)
inner_colors = cmap(np.array([1, 2, 5, 6, 9, 10]))

#ax.pie(vals.sum(axis=1), radius=3, colors=outer_colors,
 #      wedgeprops=dict(width=size, edgecolor='w'))
ax.pie(sizes, labels=labels, radius=3, colors=outer_colors,rotatelabels=True,
        wedgeprops=dict(width=size, edgecolor='w'))
    
    
#ax.pie(vals.flatten(), radius=1-size, colors=inner_colors,
 #      wedgeprops=dict(width=size, edgecolor='w'))
ax.pie(sizes_vegefruit, labels=labels_vegefruit, radius=2, colors=inner_colors,rotatelabels=True,
       wedgeprops=dict(width=size, edgecolor='w'))

#ax.set(aspect="equal", title='Total Hospital Beds and Beds/1k Population')
#ax.set(aspect="equal")
plt.title('Total Hospital Beds and Beds/1k Population',y=2)
#plt.tight_layout()
plt.show()
In [48]:
fig, ax = plt.subplots(figsize=(10,8),subplot_kw=dict(aspect="equal"))
res= f['Total Hospital Beds']
#vals = np.array([[60., 32.], [37., 40.], [29., 10.]])
labels = f['Location']
sizes = f['Total Hospital Beds']


cmap = plt.get_cmap("tab20c")
outer_colors = cmap(np.arange(3)*4)

wedges,texts=ax.pie(sizes,labels=labels, colors=outer_colors,startangle=90,rotatelabels=True,
        wedgeprops=dict(width=0.5, edgecolor='w'))

bbox_props = dict(boxstyle="square,pad=0.3", fc="w", ec="k", lw=0.72)
kw = dict(arrowprops=dict(arrowstyle="-"),
          bbox=bbox_props, zorder=0, va="center")

for i, p in enumerate(wedges):
    ang = (p.theta2 - p.theta1)/2. + p.theta1
    y = np.sin(np.deg2rad(ang))
    x = np.cos(np.deg2rad(ang))
    horizontalalignment = {-1: "right", 1: "left"}[int(np.sign(x))]
    connectionstyle = "angle,angleA=0,angleB={}".format(ang)
    kw["arrowprops"].update({"connectionstyle": connectionstyle})
    ax.annotate(res[i], xy=(x, y), xytext=(1.35*np.sign(x), 1.4*y),
                horizontalalignment=horizontalalignment, **kw)

plt.title('Total Hospital Beds',y=1.2)
plt.tight_layout()
plt.show()
In [49]:
g=pd.read_csv(r'E:\Dataset\raw_data (16).csv', skiprows=2)
pd.set_option('display.max_colwidth', None)
pd.set_option("display.max_columns",None)
pd.set_option("display.max_rows",None)
In [50]:
g.drop(g.loc[52:].index,inplace=True)
In [51]:
g.sample(5)
Out[51]:
Location State/Local Government Non-Profit For-Profit Total
32 New Mexico 0.3 0.7 0.7 1.8
28 Nebraska 0.5 2.9 0.1 3.6
9 District of Columbia NaN 3.5 0.9 4.4
0 United States 0.3 1.7 0.4 2.4
15 Indiana 0.4 1.9 0.4 2.7
In [52]:
plt.style.use('seaborn')
g=g.replace(np.nan,0)
In [53]:
plt.figure(figsize=(10,8))
state=g['State/Local Government']
non=g['Non-Profit']
forp=g['For-Profit']
loc=g['Location']
plt.scatter(state,loc,edgecolor='black',linewidth=1,alpha=0.75,label='State\Local Government Hospital')
plt.scatter(non,loc,edgecolor='black',linewidth=1,alpha=0.75,label='Non-Profit Hospital')
plt.scatter(forp,loc,edgecolor='black',linewidth=1,alpha=0.75,label='For-Profit Hospital')
plt.legend()

plt.xlabel('Hospital Beds/1k population')
plt.title('Hospitals Beds/1k population by Ownership type')
plt.tight_layout()
plt.show()
In [54]:
h=pd.read_csv(r'E:\Dataset\raw_data (17).csv', skiprows=2)
pd.set_option('display.max_colwidth', None)
pd.set_option("display.max_columns",None)
pd.set_option("display.max_rows",None)
h.drop(h.loc[52:].index,inplace=True)
In [55]:
h=h.replace(np.nan,0)
In [56]:
h.loc[:, h.columns != 'Location']=h.loc[:, h.columns != 'Location'].astype(int)
In [57]:
state=h['State/Local Government']
nonprofit=h['Non-Profit']
forprofit=h['For-Profit']
location=h['Location']

fig = plt.figure(figsize=(10,8))
ax = fig.add_subplot(111, projection='3d')



colors = ['r', 'g', 'b']
yticks = [2, 1, 0]
for c, k in zip(colors, yticks):
    
    xs = location
    ys = state
    
    cs = [c] * len(xs)
    cs[0] = 'c'

    ax.bar(xs, ys, zs=k, zdir='y', color=cs, alpha=0.8)
    
ax.set_xlabel('X')
ax.set_ylabel('Y')
ax.set_zlabel('Z')

ax.set_yticks(yticks)

plt.show()
In [58]:
i=pd.read_csv(r'E:\Dataset\raw_data (21).csv', skiprows=2)
pd.set_option('display.max_colwidth', None)
pd.set_option("display.max_columns",None)
pd.set_option("display.max_rows",None)
i.drop(i.loc[52:].index,inplace=True)
In [59]:
j=pd.read_csv(r'E:\Dataset\raw_data (22).csv', skiprows=2)
pd.set_option('display.max_colwidth', None)
pd.set_option("display.max_columns",None)
pd.set_option("display.max_rows",None)
j.drop(j.loc[52:].index,inplace=True)
j=j.drop(['Footnotes'],axis=1)
In [60]:
k=pd.read_csv(r'E:\Dataset\raw_data (23).csv', skiprows=2)
pd.set_option('display.max_colwidth', None)
pd.set_option("display.max_columns",None)
pd.set_option("display.max_rows",None)
k.drop(k.loc[52:].index,inplace=True)
In [61]:
DF= pd.concat([i,j,k], axis = 1, levels=0).sort_index(axis=1)
In [62]:
DF.sample()
Out[62]:
ICU Beds ICU Beds per 10,000 Population Location Location Location Primary Care Physicians Specialist Physicians Total Total Residents
9 401.0 6.0 District of Columbia District of Columbia District of Columbia 3204.0 4271.0 7475.0 667900.0
In [63]:
DF = DF.loc[:,~DF.columns.duplicated()]
In [64]:
DF.sample()
Out[64]:
ICU Beds ICU Beds per 10,000 Population Location Primary Care Physicians Specialist Physicians Total Total Residents
34 3168.0 3.2 North Carolina 13587.0 15231.0 28818.0 10044400.0
In [65]:
DF.set_index('Location',inplace=True)
In [66]:
DF.rename(columns = {'Total':'Total Physicians'}, inplace = True)
In [67]:
DF.head()
Out[67]:
ICU Beds ICU Beds per 10,000 Population Primary Care Physicians Specialist Physicians Total Physicians Total Residents
Location
United States 85247.0 2.7 486405.0 535601.0 1022006.0 318498500.0
Alabama 1870.0 3.9 5845.0 6320.0 12165.0 4752600.0
Alaska 130.0 1.8 1063.0 835.0 1898.0 709100.0
Arizona 1742.0 2.5 8633.0 9446.0 18079.0 7004300.0
Arkansas 856.0 2.9 3563.0 3726.0 7289.0 2921300.0
In [68]:
DF.dtypes
Out[68]:
ICU Beds                          float64
ICU Beds per 10,000 Population    float64
Primary Care Physicians           float64
Specialist Physicians             float64
Total Physicians                  float64
Total Residents                   float64
dtype: object
In [69]:
DF.style.background_gradient(cmap='Blues',subset=["ICU Beds"])\
                        .background_gradient(cmap='Reds',subset=["ICU Beds per 10,000 Population"])\
                        .format("{:.1f}")\
                        .background_gradient(cmap='Greens',subset=["Primary Care Physicians"])\
                        .background_gradient(cmap='Purples',subset=["Specialist Physicians"])\
                        .background_gradient(cmap='Pastel1_r',subset=["Total Physicians"])\
                        .background_gradient(cmap='YlOrBr',subset=["Total Residents"])\
                        .format("{:.0f}",subset=["Primary Care Physicians","Specialist Physicians","Total Physicians","ICU Beds","Total Residents"])
Out[69]:
ICU Beds ICU Beds per 10,000 Population Primary Care Physicians Specialist Physicians Total Physicians Total Residents
Location
United States 85247 2.7 486405 535601 1022006 318498500
Alabama 1870 3.9 5845 6320 12165 4752600
Alaska 130 1.8 1063 835 1898 709100
Arizona 1742 2.5 8633 9446 18079 7004300
Arkansas 856 2.9 3563 3726 7289 2921300
California 8131 2.1 54580 59418 113998 38745900
Colorado 1770 3.2 7368 7381 14749 5555200
Connecticut 731 2.1 7124 8733 15857 3466300
Delaware 249 2.7 1591 1611 3202 937700
District of Columbia 401 6.0 3204 4271 7475 667900
Florida 6226 3.0 27791 30012 57803 20843500
Georgia 2703 2.6 12675 13002 25677 10212800
Hawaii 219 1.6 1882 1825 3707 1354800
Idaho 333 1.9 1669 1362 3031 1719600
Illinois 3426 2.8 22318 21782 44100 12438400
Indiana 2358 3.6 8221 8758 16979 6487100
Iowa 622 2.0 4627 4201 8828 3056800
Kansas 878 3.1 4097 3868 7965 2814700
Kentucky 1447 3.3 5519 6522 12041 4320300
Louisiana 1518 3.4 6392 7622 14014 4519300
Maine 288 2.2 2524 2282 4806 1299500
Maryland 1227 2.1 11084 14062 25146 5870800
Massachusetts 1555 2.3 15815 21139 36954 6659900
Michigan 2749 2.8 18763 20921 39684 9770000
Minnesota 1277 2.3 8891 9483 18374 5489000
Mississippi 931 3.2 3245 3434 6679 2879400
Missouri 2092 3.5 9594 11124 20718 5934500
Montana 248 2.4 1184 1141 2325 1034000
Nebraska 548 2.9 2936 2763 5699 1868900
Nevada 1118 3.7 3093 3130 6223 2983400
New Hampshire 252 1.9 2064 2265 4329 1310300
New Jersey 1882 2.2 14907 15984 30891 8728300
New Mexico 460 2.2 2967 2923 5890 2045300
New York 4420 2.3 41076 50765 91841 19016900
North Carolina 3168 3.2 13587 15231 28818 10044400
North Dakota 278 3.8 1162 919 2081 730600
Ohio 3622 3.2 19942 23228 43170 11355900
Oklahoma 1164 3.1 4862 4747 9609 3816100
Oregon 837 2.0 6053 6191 12244 4110800
Pennsylvania 3643 2.9 24884 27444 52328 12388100
Rhode Island 279 2.8 2665 2661 5326 1014000
South Carolina 1459 3.0 6478 6594 13072 4929800
South Dakota 150 1.8 1106 969 2075 848700
Tennessee 2309 3.5 8904 10241 19145 6586400
Texas 7149 2.6 31085 34548 65633 28024000
Utah 687 2.2 3169 3771 6940 3105900
Vermont 94 1.6 1135 1225 2360 600600
Virginia 2007 2.5 11713 11826 23539 8182100
Washington 1493 2.0 11148 11167 22315 7368000
West Virginia 643 3.7 2941 2897 5838 1752300
Wisconsin 1506 2.7 8616 9291 17907 5662800
Wyoming 102 1.8 650 540 1190 560300
In [70]:
n=pd.read_csv(r'E:\Dataset\usa_county_wise.csv')
In [71]:
n.head(5)
Out[71]:
UID iso2 iso3 code3 FIPS Admin2 Province_State Country_Region Lat Long_ Combined_Key Date Confirmed Deaths
0 16 AS ASM 16 60.0 NaN American Samoa US -14.2710 -170.1320 American Samoa, US 1/22/20 0 0
1 316 GU GUM 316 66.0 NaN Guam US 13.4443 144.7937 Guam, US 1/22/20 0 0
2 580 MP MNP 580 69.0 NaN Northern Mariana Islands US 15.0979 145.6739 Northern Mariana Islands, US 1/22/20 0 0
3 630 PR PRI 630 72.0 NaN Puerto Rico US 18.2208 -66.5901 Puerto Rico, US 1/22/20 0 0
4 850 VI VIR 850 78.0 NaN Virgin Islands US 18.3358 -64.8963 Virgin Islands, US 1/22/20 0 0
In [72]:
n=n.drop(['Country_Region','Admin2','code3'],axis=1)
In [73]:
n.shape
Out[73]:
(538065, 11)
In [74]:
newdf=n.head(200000)
In [75]:
fig = px.scatter_geo(newdf, locations='FIPS', locationmode='ISO-3',
                     lat= 'Lat',
                     lon='Long_',
                     color=np.power(newdf["Confirmed"],0.3)-2 , 
                     size= np.power(newdf["Confirmed"]+1,0.3)-1,
                     hover_name='Combined_Key',
                     hover_data=['Confirmed'],
                     range_color= [0, max(np.power(newdf["Confirmed"],0.3))], 
                     projection="albers usa", animation_frame="Date", 
                     color_continuous_scale=px.colors.sequential.Plasma,
                     title='COVID-19: Progression of spread'
                    )
fig.update_coloraxes(colorscale="hot")
fig.update(layout_coloraxis_showscale=False)
fig.show()
In [ ]: